• 제어로봇시스템학회:학술대회논문집
• /
• 1994.10a
• /
• pp.134-139
• /
• 1994

In this paper the comparison between the neural networks and traditional approaches as system identification method are considered. Two model structures of neural networks are the state space model and the input output model neural networks. The traditional methods are the AutoRegressive eXogeneous Input model and the Nonlinear AutoRegressive eXogeneous Input model. The examples considered do not represent any physical system, no a priori knowledge concerning their structure has been used in the identification process. Testing inputs for comparison are the sinusoidal, ramp and the noise ramp.

• Journal of KIISE:Software and Applications
• /
• v.27 no.6
• /
• pp.632-641
• /
• 2000

Conventional character extraction methods extract character regions using methods such as color reduction, region split and merge and texture analysis from the whole image. Because these methods use many heuristic variables and thresholding values derived from a priori knowledge, it is difficult to generalize them algorithmically. In this paper, we propose a method that can extract character regions using a topographical feature extraction method and a point-line-region extension method. The proposed method can also solve the problems of conventional methods by reducing heuristic variables and generalizing thresholding values. We see that character regions can be extracted by generalized variables and thresolding values without using a priori knowledge of character region. Experimental results show that the candidate region extraction rate is 100%, and the character region extraction rate is over 98%.

• Journal of Digital Convergence
• /
• v.6 no.4
• /
• pp.177-183
• /
• 2008

This paper aims to offer a solution based on intelligent document classification to create a user-centric information retrieval system allowing user-centric linguistic expression. So, structures expressing user intention and fine document classifying process using EBL, similarity, knowledge base, user intention, are proposed. To overcome the problem requiring huge and exact semantic information, a hybrid process is designed integrating keyword, thesaurus, probability and user intention information. User intention tree hierarchy is build and a method of extracting group intention between key words and user intentions is proposed. These structures and processes are implemented in HDCI(Hybrid Document Classification with Intention) system. HDCI consists of analyzing user intention and classifying web documents stages. Classifying stage is composed of knowledge base process, similarity process and hybrid coordinating process. With the help of user intention related structures and hybrid coordinating process, HDCI can efficiently categorize web documents in according to user's complex linguistic expression with small priori information.

• Journal of information and communication convergence engineering
• /
• v.7 no.4
• /
• pp.539-544
• /
• 2009

An estimation of 3D velocity field including occluded parts without maxing tracer to the fluid had not only never been proposed but also impossible by the conventional computer vision algorithm. In this paper, we propose a new method of three dimensional optical flow of the fluid based on physical model, where some boundary conditions are given from a priori knowledge of the flow configuration. Optical flow is obtained by minimizing the mean square errors of a basic constraint and the matching error terms with visual data using Euler equations. Here, Navier-Stokes motion equations and the differences between occluded data and observable data are employed as the basic constrains. we verify the effectiveness of our proposed method by applying our algorithm to simulated data with partly artificially deleted and recovering the lacking data. Next, applying our method to the fluid of observable surface data and the knowledge of boundary conditions, we demonstrate that 3D optical flow are obtained by proposed algorithm.

• Educational Technology International
• /
• v.9 no.1
• /
• pp.49-77
• /
• 2008

As clearly suggested in the case of Wikipedia, collective intelligence is predicted to develop into the most important platform of knowledge and information in the future society. But it just remains at the level of activities for group projects in the present frame of education and so it doesn't lead to creating collective intelligence. This study looks into an 'information repository model of collective intelligence' that makes it possible to deliver an education process a priori of Shared Knowledge Reservoir to "Junior Digital Nomad", who is definitely and will be in existence, and that further enables them to be active there in reality. Based on this storage model, it suggests a practicable web system model; Junior Maphistory e-encyclopedia, which is appropriately consistent with the features of Web 2.0 and can grow into a general historical and geographical information service.

• Proceedings of the KSR Conference
• /
• 2000.11a
• /
• pp.680-687
• /
• 2000

In this paper we present a new vector control scheme for induction motor. An exact knowledge of the rotor flux position is essential for a high-performance vector control. The position of the rotor flux is measured in the direct scheme or estimated in the indirect schemes. Since the estimation of the flux position requires a priori knowledge of the induction motor parameters, the indirect schemes are machine parameter dependent. The rotor resistance and stator resistance among the parameters change with temperature. Variations in the parameters of induction machine cause deterioration of both the steady state and dynamic operation of the induction motor drive. Several methods have been presented to minimize the consequences of parameter sensitivity in indirect scheme. In this paper new estimation scheme of rotor flux position is presented to eliminate sensitivity due to resistance change with temperature. Simulation results are used to verify the performance of the proposed vector control scheme.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2246-2248
• /
• 2001

This paper presents a new vector control scheme for induction motor. An exact knowledge of the rotor flux position is essential for a high-performance vector control. The position of the rotor flux is measured in the direct schemes and estimated in the indirect schemes. Since the estimation of the flux position requires a priori knowledge of the induction motor parameters, the indirect schemes are machine parameter dependent. The rotor and stator resistance among the parameters change with temperature. Variations in the parameters of induction machine cause deterioration of both the steady state and dynamic operation of the induction motor drive. Several methods have presented to minimize the consequences of parameter sensitivity in indirect scheme. In this paper, new estimation scheme of rotor flux position is presented to eliminate sensitivity due to variation in the resistance. The simulation is executed to verify the proposed vector control performance and to compare its performance with that of indirect and direct vector control.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.7
• /
• pp.540-547
• /
• 2004

Since speech enhancement algorithms based on Kalman/Wiener filter require a priori knowledge of the noise and have focused on the minimization of the variance of the estimation error between clean and estimated speech signal, small estimation error on the noise statistics may lead to large estimation error. However, H/sub ∞/ filter does not require any assumptions and a priori knowledge of the noise statistics, but searches the best estimated signal among the entire estimated signal by applying least upper bound, consequently it is more robust to the variation of noise statistics than Kalman/Wiener filter. In this paper, we Propose a speech enhancement method using HMM and multi H/sub ∞/ filters. First, HMM parameters are estimated with the training data. Secondly, speech is filtered with multiple number of H/sub ∞/ filters. Finally, the estimation of clean speech is obtained from the sum of the weighted filtered outputs. Experimental results shows about 1dB∼2dB SNR improvement with a slight increment of computation compared with the Kalman filter method.

• Speech Sciences
• /
• v.11 no.4
• /
• pp.75-88
• /
• 2004

In this paper, we propose a new approach to sequential linear regression adaptation of continuous density hidden Markov models (CDHMMs) based on transformation space model (TSM). The proposed TSM which characterizes the a priori knowledge of the training speakers associated with maximum likelihood linear regression (MLLR) matrix parameters is effectively described in terms of the latent variable models. The TSM provides various sources of information such as the correlation information, the prior distribution, and the prior knowledge of the regression parameters that are very useful for rapid adaptation. The quasi-Bayes (QB) estimation algorithm is formulated to incrementally update the hyperparameters of the TSM and regression matrices simultaneously. Experimental results showed that the proposed TSM approach is better than that of the conventional quasi-Bayes linear regression (QBLR) algorithm for a small amount of adaptation data.

• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.5
• /
• pp.600-613
• /
• 1999

This paper focuses on development of a performance manager for IEEE 802.4 token bus networks to serve large-scale integrated systems. In order to construct the management algorithm, the principles of fuzzy logic, genetic algorithm, and neural network have been combined to represent human knowledge and to imitate of human inference mechanism. Through the simulation experiments, it is shown that the proposed performance manager is capable of improving the network performance without a priori knowledge.